# WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization

arXiv: https://arxiv.org/abs/2603.04956 · HTML: https://mlsanity.com/paper/2603.04956/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [QuIP: 2-Bit Quantization of Large Language Models With Guarantees](https://mlsanity.com/paper/2307.13304/) (2023)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws](https://mlsanity.com/paper/2404.05405/) (2024)
- [FlatQuant: Flatness Matters for LLM Quantization](https://mlsanity.com/paper/2410.09426/) (2024)
- [QTIP: Quantization with Trellises and Incoherence Processing](https://mlsanity.com/paper/2406.11235/) (2024)
- [An empirical study of LLaMA3 quantization: from LLMs to MLLMs](https://mlsanity.com/paper/2404.14047/) (2024)
- [PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression](https://mlsanity.com/paper/2405.14852/) (2024)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization](https://mlsanity.com/paper/2502.02631/) (2025)
- [Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling](https://mlsanity.com/paper/2512.02010/) (2025)
- [GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance](https://mlsanity.com/paper/2505.07004/) (2025)
- [Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization](https://mlsanity.com/paper/2505.11695/) (2025)
- [NestQuant: Nested Lattice Quantization for Matrix Products and LLMs](https://mlsanity.com/paper/2502.09720/) (2025)
- [Model-Preserving Adaptive Rounding](https://mlsanity.com/paper/2505.22988/) (2025)
- [QuEST: Stable Training of LLMs with 1-Bit Weights and Activations](https://mlsanity.com/paper/2502.05003/) (2025)
- [The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm](https://mlsanity.com/paper/2507.18553/) (2025)
- [Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos](https://mlsanity.com/paper/2508.04853/) (2025)
- [Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-aware Cache Compression](https://mlsanity.com/paper/2505.06901/) (2025)
- [Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models](https://mlsanity.com/paper/2506.19697/) (2025)
- [The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithm](https://mlsanity.com/paper/2508.01077/) (2025)
- [any4: Learned 4-bit Numeric Representation for LLMs](https://mlsanity.com/paper/2507.04610/) (2025)
- [Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models](https://mlsanity.com/paper/2510.10964/) (2025)
- [Microbenchmarking NVIDIA's Blackwell Architecture: An in-depth Architectural Analysis](https://mlsanity.com/paper/2512.02189/) (2025)

## Built on by (most cited first, 7 of 7)

- [HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization](https://mlsanity.com/paper/2605.29843/) (2026)
- [High-Rate Quantized Matrix Multiplication II](https://mlsanity.com/paper/2605.13768/) (2026)
- [SoftWater: Class-Aware Rate Allocation for Softmax Quantization](https://mlsanity.com/paper/2608.12026/) (2026)
- [Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State](https://mlsanity.com/paper/2608.15810/) (2026)
- [WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians](https://mlsanity.com/paper/2609.14706/) (2026)
- [OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization](https://mlsanity.com/paper/2610.08231/) (2026)
- [When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits](https://mlsanity.com/paper/2610.16020/) (2026)

## Abstract (arXiv)

This paper considers the problem of converting a given dense linear layer to low precision. The tradeoff between compressed length and output discrepancy is analyzed information theoretically (IT). It is shown that a popular GPTQ algorithm may have an arbitrarily large gap to the IT limit. To alleviate this problem, a novel algorithm, termed ``WaterSIC'', is proposed and is shown to be within a rate gap of 0.255 bits to the IT limit, uniformly over all possible covariance matrices of input activations. The key innovation of WaterSIC's is to allocate different quantization rates to different columns (in-features) of the weight matrix, mimicking the classical IT solution known as "waterfilling". Applying WaterSIC to the Llama and Qwen family of LLMs establishes new state-of-the-art performance for all quantization rates from 1 to 4 bits. Our code is available at https://github.com/egorlifar/watersic.